上一篇文章《当Batch Size增大时，学习率该如何随之变化？》我们从多个角度讨论了学习率与Batch Size之间的缩放规律，其中对于Adam优化器我们采用了SignSGD近似，这是分析Ad...| spaces.ac.cn
随着算力的飞速进步，有越多越多的场景希望能够实现“算力换时间”，即通过堆砌算力来缩短模型训练时间。理想情况下，我们希望投入$n$倍的算力，那么达到同样效果的时间则缩短为$1/n$，此时总的算力成...| spaces.ac.cn
In current deep learning tasks, Adam style optimizers such as Adam, Adagrad, RMSProp, Adafactor, and Lion have been widely used as alternatives to SGD style optimizers. These optimizers typically update model parameters using the sign of gradients, resulting in more stable convergence curves. The learning rate and the batch size are the most critical hyperparameters for optimizers, which require careful tuning to enable effective convergence. Previous research has shown that the optimal learn...| papers.cool
In an increasing number of domains it has been demonstrated that deep learning models can be trained using relatively large batch sizes without sacrificing data efficiency. However the limits of this massive data parallelism seem to differ from domain to domain, ranging from batches of tens of thousands in ImageNet to batches of millions in RL agents that play the game Dota 2. To our knowledge there is limited conceptual understanding of why these limits to batch size differ or how we might c...| papers.cool
在之前的文章《当Batch Size增大时，学习率该如何随之变化？》和《Adam的epsilon如何影响学习率的Scaling Law？》中，我们从理论上讨论了学习率随Batch Size的变化...| spaces.ac.cn
事实上，除了写博客内容，在这几年里，笔者是花了相当一部分时间来做科学空间的“表面功夫”，为此还专门学了一点php、css和js。虽然不敢说精益求精，但总体来说网站的浏览体验应该比前几年要好得多。...| spaces.ac.cn